CAFA-evaluator: A Python Tool for Benchmarking Ontological Classification Methods

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Piovesan, Damiano, Zago, Davide, Joshi, Parnal, Kaluza, M. Clara De Paolis, Mehdiabadi, Mahta, Ramola, Rashika, Monzon, Alexander Miguel, Reade, Walter, Friedberg, Iddo, Radivojac, Predrag, Tosatto, Silvio C. E.
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916156306096128
author Piovesan, Damiano
Zago, Davide
Joshi, Parnal
Kaluza, M. Clara De Paolis
Mehdiabadi, Mahta
Ramola, Rashika
Monzon, Alexander Miguel
Reade, Walter
Friedberg, Iddo
Radivojac, Predrag
Tosatto, Silvio C. E.
author_facet Piovesan, Damiano
Zago, Davide
Joshi, Parnal
Kaluza, M. Clara De Paolis
Mehdiabadi, Mahta
Ramola, Rashika
Monzon, Alexander Miguel
Reade, Walter
Friedberg, Iddo
Radivojac, Predrag
Tosatto, Silvio C. E.
contents We present CAFA-evaluator, a powerful Python program designed to evaluate the performance of prediction methods on targets with hierarchical concept dependencies. It generalizes multi-label evaluation to modern ontologies where the prediction targets are drawn from a directed acyclic graph and achieves high efficiency by leveraging matrix computation and topological sorting. The program requirements include a small number of standard Python libraries, making CAFA-evaluator easy to maintain. The code replicates the Critical Assessment of protein Function Annotation (CAFA) benchmarking, which evaluates predictions of the consistent subgraphs in Gene Ontology. Owing to its reliability and accuracy, the organizers have selected CAFA-evaluator as the official CAFA evaluation software.
format Preprint
id arxiv_https___arxiv_org_abs_2310_06881
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CAFA-evaluator: A Python Tool for Benchmarking Ontological Classification Methods
Piovesan, Damiano
Zago, Davide
Joshi, Parnal
Kaluza, M. Clara De Paolis
Mehdiabadi, Mahta
Ramola, Rashika
Monzon, Alexander Miguel
Reade, Walter
Friedberg, Iddo
Radivojac, Predrag
Tosatto, Silvio C. E.
Quantitative Methods
Performance
We present CAFA-evaluator, a powerful Python program designed to evaluate the performance of prediction methods on targets with hierarchical concept dependencies. It generalizes multi-label evaluation to modern ontologies where the prediction targets are drawn from a directed acyclic graph and achieves high efficiency by leveraging matrix computation and topological sorting. The program requirements include a small number of standard Python libraries, making CAFA-evaluator easy to maintain. The code replicates the Critical Assessment of protein Function Annotation (CAFA) benchmarking, which evaluates predictions of the consistent subgraphs in Gene Ontology. Owing to its reliability and accuracy, the organizers have selected CAFA-evaluator as the official CAFA evaluation software.
title CAFA-evaluator: A Python Tool for Benchmarking Ontological Classification Methods
topic Quantitative Methods
Performance
url https://arxiv.org/abs/2310.06881